Unsupervised Bayesian Non Parametric approach for Non-Intrusive Load Monitoring based on time of usage

• Published in: Neurocomputing (Amsterdam) 2021-05, Vol.435, p.239-252
• Main Authors: Salem, Hajer, Sayed-Mouchaweh, Moamar, Tagina, Moncef
• Format: Article
• Language: English
• Subjects: Bayesian Non-parametric models; Infinite Factorial Hidden Markov Models; Non Intrusive Load Monitoring (NILM); Power disaggregation
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2020.12.096

•A new infinite Factorial Hidden Markov Model conditioned on Contextual features (iFHMMCC) is proposed where its state matrix is conditioned on time of usage in addition to the transition matrix.•A new stochastic process that defines a distribution over the state matrix and the time of usage matrix of the iFHMMCC is proposed.•A stick-breaking construction that computes the probability of an appliance being active during a time period or not is proposed.•A blocked Gibbs sampling algorithm that performs a forward-filtering backwards-sampling (FFBS) for each Markov chain is developed for the iFHMMCC model.•A blocked Gibbs sampling algorithm that slice samples on the conditional probability of active chains given the time of usage probability matrix are proposed. Infinite Factorial Hidden Markov Model (iFHMM) is an attractive extension of Factorial Hidden Markov Model for Non-Intrusive Load Monitoring (NILM) which infers automatically the number of appliances in households and adapts its effective model complexity to fit the data. However, due to the infinite dimension nature of the model, its inference is difficult and faces several issues in the context of NILM. First, the model is hindered by computational complexity because it cannot deal with a number of appliances greater than ten. Second, it still requires accuracy improvement. Third, the model convergence may take a too long time. Therefore, a new infinite Factorial Hidden Markov Model constrained on Contextual features (iFHMMCC) is developed to overcome these shortcomings. To this end, appliances’ time of usage is added to the model in order improve disaggregation accuracy. Besides, it is used to alleviate the inference’s computational complexity and makes the model more tractable than Bayesian Non-Parametric (BNP) state of the art algorithms. Evaluation is performed on REDD database and the proposed approach is compared to five different well-known BNP disaggregation algorithms. The obtained results demonstrate an encouraging improvement in disaggregation accuracy as well as the inference’s computational complexity.